	Claude 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4.1 Fast
Score	4th 76.4%	7th 76.0%	2nd 77.2%	3rd 77.2%	19th 70.4%	16th 71.5%	8th 75.0%	13th 74.3%	9th 74.9%	12th 74.3%	6th 76.2%	15th 73.5%	11th 74.8%	10th 74.8%	5th 76.3%	1st 77.6%	20th 69.8%	21st 68.5%	14th 74.0%	17th 71.3%	18th 70.7%
80.2%	83%	82%	79%	85%	60%	73%	78%	81%	86%	79%	86%	90%	81%	81%	83%	83%	80%	74%	82%	81%	77%
68.8%	70%	62%	73%	69%	28%	77%	67%	67%	61%	69%	82%	81%	68%	75%	71%	73%	76%	60%	82%	66%	67%
51.4%	55%	47%	55%	54%	44%	57%	54%	57%	44%	54%	59%	51%	44%	51%	51%	47%	57%	51%	47%	44%	57%
80.9%	81%	81%	81%	82%	81%	77%	80%	81%	78%	83%	77%	86%	83%	68%	80%	85%	90%	84%	72%	82%	86%
85.3%	87%	91%	80%	87%	84%	75%	86%	91%	95%	91%	87%	82%	86%	88%	79%	91%	88%	86%	86%	73%	79%
86.6%	79%	85%	79%	91%	85%	91%	88%	94%	84%	84%	90%	77%	94%	87%	88%	84%	92%	93%	84%	79%	91%
85.6%	87%	88%	90%	90%	91%	88%	82%	90%	93%	81%	85%	84%	84%	91%	81%	89%	96%	62%	83%	77%	86%
75.0%	79%	78%	77%	77%	83%	49%	80%	79%	77%	77%	68%	77%	77%	62%	79%	82%	70%	68%	59%	83%	93%
72.2%	80%	69%	69%	70%	64%	53%	66%	63%	79%	82%	76%	71%	75%	76%	79%	73%	79%	71%	68%		80%
84.0%	87%	79%	82%	90%	86%	86%	85%	81%	85%	89%	85%	78%	89%	86%	83%	80%	69%	83%	86%	86%	90%
70.3%	73%	76%	79%	76%	68%	95%	76%	85%	64%	52%	76%	74%	52%	55%	70%	68%	44%	43%	84%	83%	83%
67.7%	72%	73%	73%	76%	76%	71%	69%	68%	73%	60%	73%	68%	60%	66%	73%	68%	51%	57%	72%	64%	58%
69.9%	58%	74%	75%	77%	76%	80%	74%	72%	81%	75%	72%	72%	75%	76%	81%	67%	53%	53%	71%	53%	53%
77.5%	74%	80%	74%	74%	80%	70%	75%	81%	82%	80%	76%	73%	80%	70%	80%	80%	77%	84%	79%	81%	78%
75.4%	76%	71%	80%	83%	74%	74%	78%	74%	75%	74%	79%	70%	82%	79%	75%	79%	74%	68%	72%	75%	72%
77.9%	82%	81%	83%	70%	62%	82%	81%	69%	72%	77%	88%	92%	77%	88%	78%	88%	60%	75%	87%	76%	67%
78.4%	81%	74%	84%	84%	74%	75%	82%	77%	84%	70%	87%	77%	70%	81%	85%	83%	84%	66%	77%	71%	81%
64.8%	72%	67%	65%	68%	83%	49%	67%	67%	67%	65%	51%	59%	63%	58%	73%	69%	67%	53%	53%	67%	78%
48.1%	51%	34%	51%	45%	57%	32%	49%	53%	57%	57%	39%	31%	60%	65%	63%	69%	52%	38%	34%	44%	30%
73.3%	79%	80%	79%	78%	71%	64%	78%	75%	73%	83%	70%	67%	74%	66%	73%	83%	67%	68%	71%	67%	74%
72.9%	72%	75%	95%	83%	72%	67%	84%	68%	75%	82%	78%	68%	74%	73%	74%	79%	63%	62%	56%	69%	62%
71.4%	78%	77%	73%	73%	51%	67%	75%	78%	75%	77%	66%	74%	77%	66%	79%	75%	72%	63%	63%	69%	71%
59.4%	62%	54%	54%	54%	74%	75%	66%	68%	56%	67%	59%	64%	67%	72%	49%	58%	49%	44%	64%	47%	44%
66.8%	64%	75%	80%	77%	48%	78%	65%	67%	67%	70%	83%	56%	70%	74%	65%	70%	50%	54%	76%		48%
81.7%	88%	87%	82%	90%	82%	75%	84%	83%	84%	87%	78%	68%	83%	75%	81%	85%	84%	80%	89%	74%	76%
73.1%	69%	76%	83%	72%	75%	79%	83%	75%	75%	76%	77%	73%	73%	67%	65%	73%	60%	72%	79%	70%	63%
69.4%	81%	74%	73%	76%	74%	47%	72%	74%	66%	69%	49%	70%	70%	64%	79%	76%	66%	80%	60%	62%	76%
72.3%	74%	75%	74%	74%	67%	55%	76%	79%	80%	66%	74%	68%	76%	73%	72%	72%	75%	70%	72%	74%	72%
65.7%	70%	78%	80%	77%	68%	59%	78%	69%	75%	49%	66%	63%	54%	51%	64%	66%	54%	44%	86%	64%	65%
76.0%	77%	84%	77%	77%	69%	68%	61%	83%	80%	69%	82%	78%	75%	71%	86%	79%	71%	85%	80%	75%	69%
73.2%	74%	71%	73%	73%	50%	76%	71%	76%	76%	76%	81%	73%	76%	82%	75%	84%	59%	80%	84%	59%	69%
91.8%	89%	95%	89%	98%	98%	86%	91%	86%	98%	91%	85%	94%	98%	94%	98%	94%	91%	94%	98%	98%	63%
64.2%	67%	62%	67%	55%	55%	70%	66%	70%	55%	66%	71%	63%	55%	63%	62%	63%	70%	63%	59%	94%	52%
70.6%	85%	65%	78%	80%	73%	59%	63%	67%	70%	70%	67%	67%	67%	70%	79%	79%	64%	75%	61%	67%	77%
70.2%	83%	91%	83%	85%	34%	61%	57%	62%	71%	57%	78%	80%	72%	72%	78%	84%	63%	75%	66%	62%	61%
62.7%	72%	62%	71%	75%	64%	72%	63%	60%	52%	72%	68%	61%	63%	58%	68%	68%	60%	38%	62%	60%	48%
78.5%	84%	72%	85%	78%	87%	85%	73%	65%	81%	76%	89%	90%	83%	94%	84%	83%	60%	62%	84%	67%	67%
84.2%	83%	88%	90%	90%	100%	87%	83%	83%	90%	90%	77%	75%	86%	88%	84%	82%	67%	84%	80%	72%	89%
81.0%	80%	83%	88%	92%	65%	84%	85%	78%	82%	87%	90%	85%	90%	85%	83%	86%	64%	68%	78%	69%	78%
94.5%	98%	96%	98%	89%	89%	96%	100%	96%	89%	100%	94%	97%	89%	97%	89%	97%	96%	97%	92%	96%	89%
71.6%	73%	75%	76%	73%	59%	72%	75%	75%	70%	79%	77%	53%	80%	80%	75%	73%	78%	41%	80%	76%	63%
80.6%	88%	88%	67%	79%	74%	60%	86%	75%	75%	72%	88%	88%	83%	94%	86%	84%	82%	86%	75%	68%	94%
78.1%	70%	91%	77%	73%	73%	78%	72%	52%	70%	66%	93%	91%	80%	85%	82%	85%	77%	93%	88%	78%	66%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.